“An Explainable Hybrid 2D–3D Deep Learning Framework for Automated Lung Cancer Detection and Subtype Classification”

Read full text Summarise with VIRAT
Authors: Ms. Snehal lande, Prof. S.G. Tathe
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Lung cancer has a high mortality rate, largely due to late detection. Standard diagnostic tools, such as CT scans and X-rays, need radiologists to analyze them, which can be time-consuming and can have mistakes. This paper presents a deep learning system for the automated detection and classification of lung cancer using medical images. The system uses Convolutional Neural Networks (CNNs) and 3D-ResNet models to examine CT and X-ray images, learning about the characteristics of lung tissues. It classifies cancer into types like Small Cell Lung Cancer (SCLC) and Non-Small Cell Lung Cancer (NSCLC) with good accuracy. The method involves a multi-stage process: data collection, image preparation, segmentation, feature extraction, and classification to get consistent results. Preparation steps, like noise reduction and normalization, make images clearer, and visualization tools, like heatmaps, show affected areas, which makes the system easier for doctors to understand and use. Tests showed that the model performs well in accuracy, precision, recall, and F1-score, cutting down diagnosis time and reducing the need for people to do the work. In conclusion, this system shows how artificial intelligence can change lung cancer screening by allowing for quicker, more accurate, and bigger diagnoses. In the future, it could be used for other respiratory diseases and added to realtime hospital systems for better healthcare.

Fields of Study & Subjects

AI in cancer detection COVID-19 diagnosis using AI Lung Cancer Diagnosis and Treatment

Publication details

Journal / source
International Journal of Engineering Research and Science & Technology
Volume
22
Issue
1(S)
Pages
292–297
Publication date
21 March 2026
Language
EN